Introduction

The MenaVoice API is a REST API for text to speech and speech to text. It takes and returns JSON, accepts audio uploads as multipart form data, and authenticates every request with an API key.

​Base URL

All endpoints live under one base URL:

https://api.menavoice.ai/api

​Authentication

Send your API key in the x-api-key header:

curl https://api.menavoice.ai/api/tts \
  -H "x-api-key: $MENAVOICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text": "مرحباً", "voiceId": "layla"}'

Don't have a key yet? See Get Your API Key. Details are in Authentication.

​Endpoints

​Requests

• Send JSON bodies with Content-Type: application/json, UTF-8 encoded, up to 10 MB.
• Upload audio for transcription as multipart/form-data, up to 25 MB per file.
• Text is counted in characters, so Arabic, English and French text are billed the same way.

​Responses

Successful responses are JSON. Audio comes back base64-encoded, together with its mimeType:

{
  "audio": "SUQzBAAAAAAAI1RTU0UAAAAPAAADTGF2ZjYwLjE2LjEwMAAAAAAAAAAA...",
  "mimeType": "audio/mpeg",
  "voice": "layla",
  "characters": 6
}

Errors use standard HTTP status codes and a JSON body with a readable message:

{
  "error": "Invalid or revoked API key"
}

See Errors for every status code and which ones to retry.

​Call it from your server

Use the API from backend code. It doesn't accept cross-origin requests from other websites' browser code, and a key in front-end code would be exposed to anyone who opens your app. If your front end needs audio, have it call your server, and let your server call MenaVoice. See Going to Production.

​Pricing and limits

API requests are paid from prepaid API credit at $25 per million characters, and limited to 30 requests per minute per endpoint, with concurrency that grows with your top-ups. See Pricing & Rate Limits and Rate Limits.